MFC-RFNet: 一种多尺度引导的修正流网络用于雷达序列预测
MFC-RFNet: A Multi-scale Guided Rectified Flow Network for Radar Sequence Prediction
AI总结：
本文提出MFC-RFNet，通过多尺度通信与引导特征融合解决雷达序列预测中的多尺度演变、帧间特征错位和长程时空上下文建模问题，提升预测精度与空间保真度。
摘要：
准确且高分辨率的雷达回波序列降水nowcasting对灾害缓解和经济规划至关重要，但仍是重大挑战。关键难点包括建模复杂的多尺度演变、纠正因位移引起的帧间特征错位以及高效捕捉长程时空上下文而不牺牲空间保真度。为解决这些问题，我们提出了多尺度特征通信修正流（RF）网络（MFC-RFNet），一种整合多尺度通信与引导特征融合的生成框架。为增强多尺度融合并保留细节，波let引导跳接连接（WGSC）保留高频成分，特征通信模块（FCM）促进双向跨尺度交互。为纠正帧间位移，条件引导空间变换融合（CGSTF）从条件回波学习空间变换以对齐浅层特征。骨干网络采用修正流训练以学习近线性概率流轨迹，使少量步长采样具有稳定保真度。此外，在编码器尾部、瓶颈和第一个解码器层中放置轻量级视觉-RWKV（RWKV）块，以在低空间分辨率下以中等计算量捕捉长程时空依赖性。在四个公开数据集（SEVIR、MeteoNet、Shanghai和CIKM）上的评估显示，MFC-RFNet在强基线模型上表现出一致的改进，产生更清晰的回波形态并在更高降雨率阈值和更长的提前时间下保持技能。这些结果表明，所提出的RF训练与尺度感知通信、空间对齐和频率感知融合的协同作用为基于雷达的nowcasting提供了一种有效且稳健的方法。
英文摘要：
Accurate and high-resolution precipitation nowcasting from radar echo sequences is crucial for disaster mitigation and economic planning, yet it remains a significant challenge. Key difficulties include modeling complex multi-scale evolution, correcting inter-frame feature misalignment caused by displacement, and efficiently capturing long-range spatiotemporal context without sacrificing spatial fidelity. To address these issues, we present the Multi-scale Feature Communication Rectified Flow (RF) Network (MFC-RFNet), a generative framework that integrates multi-scale communication with guided feature fusion. To enhance multi-scale fusion while retaining fine detail, a Wavelet-Guided Skip Connection (WGSC) preserves high-frequency components, and a Feature Communication Module (FCM) promotes bidirectional cross-scale interaction. To correct inter-frame displacement, a Condition-Guided Spatial Transform Fusion (CGSTF) learns spatial transforms from conditioning echoes to align shallow features. The backbone adopts rectified flow training to learn near-linear probability-flow trajectories, enabling few-step sampling with stable fidelity. Additionally, lightweight Vision-RWKV (RWKV) blocks are placed at the encoder tail, the bottleneck, and the first decoder layer to capture long-range spatiotemporal dependencies at low spatial resolutions with moderate compute. Evaluations on four public datasets (SEVIR, MeteoNet, Shanghai, and CIKM) demonstrate consistent improvements over strong baselines, yielding clearer echo morphology at higher rain-rate thresholds and sustained skill at longer lead times. These results suggest that the proposed synergy of RF training with scale-aware communication, spatial alignment, and frequency-aware fusion presents an effective and robust approach for radar-based nowcasting.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
